自由能原理视角下的强化学习世界模型与探索|自由能原理与强化学习读书会·周日直播

导语


内容简介
内容简介
内容大纲
内容大纲
-
信息论基础
-
变分自编码器
-
变分自由能与强化学习世界模型
-
分层世界模型
-
期望自由能与强化学习探索
关键词
关键词
-
世界模型 World Model
-
强化学习探索 Reinforcement Learning Exploration
-
变分自编码器 Variational autoencoder
-
互信息 Mutual Information
-
信息增益 Information Gain
参考文献
参考文献
-
Pinkard H, Waller L. A visual introduction to information theory[J]. arXiv preprint arXiv:2206.07867, 2022.
-
Higgins I, Matthey L, Pal A, et al. beta-vae: Learning basic visual concepts with a constrained variational framework[J]. 2016.
-
Ha D, Schmidhuber J. Recurrent world models facilitate policy evolution[J]. Advances in neural information processing systems, 2018, 31.
-
Mazzaglia P, Verbelen T, Çatal O, et al. The free energy principle for perception and action: A deep learning perspective[J]. Entropy, 2022, 24(2): 301.
-
Hafner D, Lillicrap T, Fischer I, et al. Learning latent dynamics for planning from pixels. ICML 2019
-
Hafner D, Ortega P A, Ba J, et al. Action and perception as divergence minimization[J]. arXiv preprint arXiv:2009.01791, 2020.
-
Hafner D, Lillicrap T, Ba J, et al. Dream to control: Learning behaviors by latent imagination[J]. arXiv preprint arXiv:1912.01603, 2019.
-
Hafner D, Lillicrap T, Norouzi M, et al. Mastering atari with discrete world models[J]. arXiv preprint arXiv:2010.02193, 2020.
-
Hafner D, Pasukonis J, Ba J, et al. Mastering diverse domains through world models[J]. arXiv preprint arXiv:2301.04104, 2023.
-
Saxena V, Ba J, Hafner D. Clockwork variational autoencoders[J]. NIPS 2021, 34: 29246-29257.
-
Gumbsch C, Sajid N, Martius G, et al. Learning Hierarchical World Models with Adaptive Temporal Abstractions from Discrete Latent Dynamics. ICLR 2024
-
Hao J, Yang T, Tang H, et al. Exploration in deep reinforcement learning: From single-agent to multiagent domain[J]. IEEE Transactions on Neural Networks and Learning Systems, 2023.
-
Pathak D, Gandhi D, Gupta A. Self-supervised exploration via disagreement. ICML 2019
-
Sekar R, Rybkin O, Daniilidis K, et al. Planning to explore via self-supervised world models. ICML 2020
-
Shyam P, Jaśkowski W, Gomez F. Model-based active exploration. ICML, 2019
-
Houthooft R, Chen X, Duan Y, et al. Vime: Variational information maximizing exploration. NIPS 2016
-
Mazzaglia P, Catal O, Verbelen T, et al. Curiosity-driven exploration via latent bayesian surprise. AAAI 2022
主讲人
主讲人

参与方式
参与方式
时间:2024年5月12日(本周日)上午10:00-12:00

斑图地址:https://pattern.swarma.org/study_group_issue/629
自由能原理与强化学习读书会招募中

点击“阅读原文”,报名读书会





